{"id":"https://openalex.org/W2102149658","doi":"https://doi.org/10.1145/1322192.1322231","title":"Temporal filtering of visual speech for audio-visual speech recognition in acoustically and visually challenging environments","display_name":"Temporal filtering of visual speech for audio-visual speech recognition in acoustically and visually challenging environments","publication_year":2007,"publication_date":"2007-11-12","ids":{"openalex":"https://openalex.org/W2102149658","doi":"https://doi.org/10.1145/1322192.1322231","mag":"2102149658"},"language":"en","primary_location":{"id":"doi:10.1145/1322192.1322231","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1322192.1322231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th international conference on Multimodal interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100668167","display_name":"Jong\u2010Seok Lee","orcid":"https://orcid.org/0000-0002-8038-1119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jong-Seok Lee","raw_affiliation_strings":["KAIST, Daejeon, South Korea","KAIST, Daejeon , South Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Daejeon , South Korea#TAB#","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014633392","display_name":"Cheol Hoon Park","orcid":"https://orcid.org/0000-0001-7942-7311"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Cheol Hoon Park","raw_affiliation_strings":["KAIST, Daejeon, South Korea","KAIST, Daejeon , South Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST, Daejeon , South Korea#TAB#","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100668167"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.13620234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010700941085815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7090059518814087},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.608002781867981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5339276790618896},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4945187270641327},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.49282172322273254},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45180052518844604},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4445381760597229},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43294376134872437},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17609024047851562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010700941085815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7090059518814087},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.608002781867981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339276790618896},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4945187270641327},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.49282172322273254},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45180052518844604},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4445381760597229},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43294376134872437},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17609024047851562},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1322192.1322231","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1322192.1322231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th international conference on Multimodal interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W148999028","https://openalex.org/W177229737","https://openalex.org/W196476531","https://openalex.org/W1554663460","https://openalex.org/W1554901277","https://openalex.org/W1557636172","https://openalex.org/W1578856370","https://openalex.org/W1766888123","https://openalex.org/W2015394094","https://openalex.org/W2031144006","https://openalex.org/W2036205336","https://openalex.org/W2044111021","https://openalex.org/W2068309229","https://openalex.org/W2074417845","https://openalex.org/W2074796660","https://openalex.org/W2076092824","https://openalex.org/W2097283332","https://openalex.org/W2104396257","https://openalex.org/W2121486117","https://openalex.org/W2132999255","https://openalex.org/W2134723767","https://openalex.org/W2137075158","https://openalex.org/W2146614494","https://openalex.org/W2155765376","https://openalex.org/W2157190406","https://openalex.org/W2166846876","https://openalex.org/W2478884216","https://openalex.org/W2614613495","https://openalex.org/W3005368757","https://openalex.org/W4231627457","https://openalex.org/W4388297464"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2081671587","https://openalex.org/W1151175420","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,5,18,33,51,66,87],"visual":[3,26,44,68,100,116],"information":[4],"speech":[6,20,35,45,117,128],"has":[7],"been":[8],"shown":[9],"to":[10,81,93,99],"be":[11,41],"effective":[12],"for":[13,15,64,120],"compensating":[14],"performance":[16,119,130],"degradation":[17],"acoustic":[19],"recognition":[21,36,118,129],"in":[22,31,43,91,131],"noisy":[23,123,136],"environments.":[24],"However,":[25],"noise":[27],"is":[28,79],"usually":[29],"ignored":[30],"most":[32],"audio-visual":[34,127],"systems,":[37],"while":[38],"it":[39],"can":[40,112],"included":[42],"signals":[46],"during":[47],"acquisition":[48],"or":[49,104],"transmission":[50],"the":[52,71,82,110],"signals.":[53],"In":[54,70],"this":[55],"paper,":[56],"we":[57],"present":[58],"a":[59,74],"new":[60],"temporal":[61,83,96],"filtering":[62],"technique":[63],"extraction":[65],"noise-robust":[67],"features.":[69],"proposed":[72],"method,":[73],"carefully":[75],"designed":[76],"band-pass":[77],"filter":[78],"applied":[80],"pixel":[84],"value":[85],"sequences":[86],"lip":[88],"region":[89],"images":[90,124],"order":[92],"remove":[94],"unwanted":[95],"variations":[97],"due":[98],"noise,":[101],"illumination":[102],"conditions":[103],"speakers'":[105],"appearances.":[106],"We":[107],"demonstrate":[108],"that":[109],"method":[111],"improve":[113],"not":[114],"only":[115],"clean":[121],"and":[122,134],"but":[125],"also":[126],"both":[132],"acoustically":[133],"visually":[135],"conditions.":[137]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}